explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-14 18:22:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix URL tests

Browse Source
This commit is contained in:
Matthew Honnibal 2016-12-30 17:10:08 -06:00
parent 9936a1b9b5
commit 3ba7c167a8
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/tests/tokenizer/test_urls.py
View File

@ -16,12 +16,12 @@ URLS = [
# Punctuation we want to check is split away before the URL # Punctuation we want to check is split away before the URL
PREFIXES = [ PREFIXES = [
"(", '"', "...", ":", "<", ">", ")" "(", '"', "...", ">"
] ]
# Punctuation we want to check is split away after the URL # Punctuation we want to check is split away after the URL
SUFFIXES = [ SUFFIXES = [
"(", '"', "...", ":", "<", ">"] '"', ":", ">"]
@pytest.mark.parametrize("text", URLS) @pytest.mark.parametrize("text", URLS)
def test_simple_url(en_tokenizer, text): def test_simple_url(en_tokenizer, text):
@ -40,10 +40,10 @@ def test_prefixed_url(en_tokenizer, prefix, url):
@pytest.mark.parametrize("suffix", SUFFIXES) @pytest.mark.parametrize("suffix", SUFFIXES)
@pytest.mark.parametrize("url", URLS) @pytest.mark.parametrize("url", URLS)
def test_prefixed_url(en_tokenizer, suffix, url): def test_suffixed_url(en_tokenizer, url, suffix):
tokens = en_tokenizer(url + suffix) tokens = en_tokenizer(url + suffix)
assert tokens[1].text == suffix
assert tokens[0].text == url assert tokens[0].text == url
assert tokens[1].text == suffix
assert len(tokens) == 2 assert len(tokens) == 2
@pytest.mark.parametrize("prefix", PREFIXES) @pytest.mark.parametrize("prefix", PREFIXES)